fix(spend-logs): preserve error_message on ProxyException failures (#30381)

* fix(spend-logs): preserve error_message on ProxyException failures

`StandardLoggingPayloadSetup.get_error_information` used
`str(original_exception)` to populate the human-readable error message
stored in `spend_logs.metadata.error_information.error_message`.

`ProxyException` (litellm/proxy/_types.py:3453) sets `self.message` in
its constructor but does NOT call `super().__init__(message)` and does
NOT define `__str__`. As a result, `str(ProxyException(...))` returns
the empty string, and every auth/budget/quota rejection was landing
in spend_logs with `error_message=""` despite a fully populated
traceback.

Operator impact: dashboard "LLM Failure" rows became untriageable —
the only way to tell a 401 from a 429 was to manually unpack the
traceback JSON via psql. Burst failure patterns (e.g. a UI session
polling with a stale token) produced 20-30 indistinguishable
`error_code=401` rows per second.

Fix: prefer the `.message` attribute (set by ProxyException and every
litellm.exceptions.* class) over `str(exc)`. The `str(exc)` fallback
is retained for non-litellm exception types, preserving prior behavior.

Test plan:
  - 2 new unit tests in tests/test_litellm/litellm_core_utils/
    test_litellm_logging.py:
    * test_get_error_information_prefers_message_attribute_over_str
    * test_get_error_information_falls_back_to_str_when_no_message_attr
  - Existing test_get_error_information_error_code_priority still passes
  - End-to-end verified: bad-key 401 now stores full
    "Authentication Error, Invalid proxy server token passed..."
    message in spend_logs.metadata.error_information.error_message

* fix(spend-logs): preserve explicit empty .message + drop dead reference

Greptile P2 on #30381. The truthiness check `if message_attr:`
silently skipped an explicit empty-string `.message` and fell
through to `str(original_exception)`. For ProxyException-shaped
objects both produce empty, so the bug was latent; for other
exception types it would inject a different string into
error_information.error_message and corrupt the signal.

Use `is not None` so an empty string survives verbatim.

Also drop the stale `See e2e/cases/11.` comment reference — that
path does not exist anywhere in the repo and confuses future
readers.

Regression test added: an exception with `.message=""` and a
non-empty `super().__init__()` arg must yield error_message == "".

* ci: retrigger workflows after base branch change to litellm_internal_staging

litellm/litellm_core_utils/litellm_logging.py

@@ -5416,19 +5416,20 @@ class StandardLoggingPayloadSetup:
                     tb_lines[:MAXIMUM_TRACEBACK_LINES_TO_LOG]
                 )  # Limit to first 100 lines
 
+        # Prefer the `.message` attribute (set by ProxyException and every
+        # litellm.exceptions.* class) over str(exc); ProxyException does not
+        # call super().__init__() nor define __str__, so str() on it returns
+        # an empty string, which used to silently strip the human-readable
+        # message from spend_logs.metadata.error_information.
+        # Use isinstance, not truthiness: an explicit empty string on
+        # `.message` is a deliberate value and must not be replaced by
+        # `str(exc)`.
         explicit_message = getattr(original_exception, "message", None)
-        error_message = (
-            explicit_message
-            if isinstance(explicit_message, str) and explicit_message
-            else str(original_exception)
-        )
+        if isinstance(explicit_message, str):
+            error_message = explicit_message
+        else:
+            error_message = str(original_exception) if original_exception else ""
 
-        # Duck-typed read so bare-Exception subclasses like
-        # `litellm.BudgetExceededError` can participate without joining the
-        # RateLimitError hierarchy (which would break `except BudgetExceededError`).
-        # Validated against the enum value sets so a third-party exception that
-        # happens to declare a `.category` or `.rate_limit_type` string attribute
-        # can't leak garbage into the payload or Prometheus label cardinality.
         rate_limit_category = validate_rate_limit_category(
             getattr(original_exception, "category", None)
         )
@@ -5441,7 +5442,7 @@ class StandardLoggingPayloadSetup:
             error_class=error_class,
             llm_provider=_llm_provider_in_exception,
             traceback=traceback_info,
-            error_message=error_message if original_exception else "",
+            error_message=error_message,
             error_rate_limit_category=rate_limit_category,
             error_rate_limit_type=rate_limit_type,
         )

tests/test_litellm/litellm_core_utils/test_litellm_logging.py

@@ -2116,6 +2116,88 @@ def test_get_error_information_error_code_priority():
     assert result["error_class"] == "NoCodeException"
 
 
+def test_get_error_information_prefers_message_attribute_over_str():
+    """
+    Regression for empty-error_message-in-spend-logs.
+
+    ProxyException sets `self.message` but does NOT call
+    `super().__init__(message)` nor define `__str__`, so `str(exc)`
+    returns the empty string. Before the fix, get_error_information
+    used `str(original_exception)` and silently stripped the
+    human-readable message from spend_logs.metadata.error_information,
+    making dashboard "LLM Failure" rows un-triagable.
+
+    Asserts the `.message` attribute is consulted first.
+    """
+    from litellm.litellm_core_utils.litellm_logging import StandardLoggingPayloadSetup
+
+    # Simulate a ProxyException-shaped exception: .message set, but
+    # super().__init__() NOT called and no __str__ override.
+    class ProxyExceptionLike(Exception):
+        def __init__(self, message, code):
+            self.message = str(message)
+            self.code = str(code)
+            # NOTE: deliberately NOT calling super().__init__(message)
+
+    msg = "Authentication Error, Invalid proxy server token passed. key=..."
+    exc = ProxyExceptionLike(message=msg, code=401)
+
+    # Sanity check: this exception type's str() really is empty
+    assert str(exc) == "", (
+        "Test premise broken — bare-base Exception now returns message; "
+        "review whether ProxyException fix landed at the class level instead"
+    )
+
+    result = StandardLoggingPayloadSetup.get_error_information(exc)
+    assert (
+        result["error_message"] == msg
+    ), f"expected message from .message attribute, got {result['error_message']!r}"
+    assert result["error_code"] == "401"
+    assert result["error_class"] == "ProxyExceptionLike"
+
+
+def test_get_error_information_preserves_explicit_empty_message():
+    """
+    An exception that deliberately sets `.message = ""` must surface
+    the empty string verbatim, not fall through to `str(exc)`.
+
+    Regression for greptile P2 finding on PR #30381: a truthiness
+    check (`if message_attr:`) would silently mask an explicit empty
+    message and substitute `str(original_exception)` — which for
+    ProxyException-shaped objects is also empty, but for plain
+    `Exception("boom")` would inject the wrong string and corrupt
+    the error_information signal.
+    """
+    from litellm.litellm_core_utils.litellm_logging import StandardLoggingPayloadSetup
+
+    class ProxyExceptionLike(Exception):
+        def __init__(self, message, code):
+            self.message = message
+            self.code = str(code)
+            super().__init__("unrelated-args-summary")
+
+    exc = ProxyExceptionLike(message="", code=500)
+    result = StandardLoggingPayloadSetup.get_error_information(exc)
+    assert result["error_message"] == "", (
+        "explicit empty .message must survive verbatim; got "
+        f"{result['error_message']!r}"
+    )
+
+
+def test_get_error_information_falls_back_to_str_when_no_message_attr():
+    """
+    Plain Exception (no `.message` attr) must still produce a useful
+    error_message via str(exc), preserving prior behavior for
+    non-litellm exception types.
+    """
+    from litellm.litellm_core_utils.litellm_logging import StandardLoggingPayloadSetup
+
+    exc = ValueError("boom")
+    result = StandardLoggingPayloadSetup.get_error_information(exc)
+    assert result["error_message"] == "boom"
+    assert result["error_class"] == "ValueError"
+
+
 # ──────────────────────────────────────────────────────────────────────
 # Tests for _get_assembled_streaming_response non-streaming early return
 # ──────────────────────────────────────────────────────────────────────